PaperILike: Human Interventions as Both Explicit and Implicit Robot Feedback
tomssilver · x · 2026-11-16
Tom Silver's weekly paper pick is "Learning from Interventions" (Spencer et al., RSS 2020). Key idea: in human-robot interaction, interventions give explicit corrections, but the choice to intervene — or not — is informative too and can serve as implicit feedback for robot learning.
More from Embodied
- Gurman: Apple smart glasses prototypes run pared-down visionOS 28, dubbed 'AirPods for your face' — Scobleizer · 2026-11-16
- Apple glasses' flagship feature revealed: Siri AI app integrations running on a paired iPhone — Scobleizer · 2026-11-16
- Microsoft details Project Helix: next-gen Xbox is 'a console that plays your PC games, not a PC' — tomwarren · 2026-11-16
- Figure CEO shows humanoid robot making a bed in a real bedroom — adcock_brett · 2026-11-16
- MIT CSAIL shares robot dog meeting a robot duck — MIT_CSAIL · 2026-11-16
- 12 robot learning researchers to follow after CoRL 2026 — KyleMorgenstein · 2026-11-16